@inproceedings{bakman-etal-2026-hair, title = "Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment", author = "Bakman, Yavuz Faruk and Yaldiz, Duygu Nur and Avestimehr, Salman and Karimireddy, Sai Praneeth", editor = "Chang, Kai-Wei and Mehrabi, Ninareh and Krishna, Satyapriya and Das, Anubrata and Dhamala, Jwala and Cao, Yang Trista and Kumarage, Tharindu and Ramakrishna, Anil and Christodoulopoulos, Christos and Wan, Yixin and Galystan, Aram and Kumar, Anoop and Gupta, Rahul", booktitle = "Proceedings of the 6th Workshop on Trustworthy {NLP} ({T}rust{NLP} 2026)", month = jul, year = "2026", address = "San Diego, California", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.trustnlp-main.10/", pages = "180--203", ISBN = "979-8-89176-418-7" }